UFC Fight Night: Nurmagomedov vs. Song  29 Aug 2026 · Oriental Sports Center, Shanghai, China, CN

Julia Polastri defeats Xiong Jingnan by KO/TKO

Loss Xiong Jingnan 19-4-0
Win Julia Polastri 15-6-0
KO/TKO · head kick

Round 1 · 3:06

Xiong Jingnan vs Polastri — Women's Strawweight · UFC Fight Night: Nurmagomedov vs. Song

Predictions summary

What happened

The result, the defining moments, and what the verdict means.

Julia Polastri defeated Xiong Jingnan by KO (head kick) at 3:06 of Round 1

Prelims

Pre-fight analysis — how we saw it going in

Case for Xiong Jingnan

Eleven of Xiong's nineteen wins are knockouts, and she has fought seven five-round fights — more than anyone else on this card. At 38 she arrives off a decision loss to Angela Hill, with three defeats in twenty-two fights and only one of them ending early.

Case for Polastri

Polastri lands 6.22 significant strikes a minute and absorbs 5.18 doing it. Twelve of her twenty fights reached the judges — and so did all six of her defeats. Nobody has finished her, which is the single most relevant fact against a puncher.

What We Were Watching For

  • Xiong has fought seven five-round fights. Nobody else on this card has fought more than three.
  • All six of Polastri's defeats are decisions. Eleven of Xiong's nineteen wins are knockouts.
  • Polastri lands 6.22 significant strikes a minute and absorbs 5.18; her 58% takedown defence is the softer number.
  • Both arrive off a loss — Xiong to Angela Hill in May, Polastri to Talita Alencar in April.
Records & career stats
Xiong Jingnan vs Polastri
Xiong Jingnan Polastri
  1. OutputSig. strikes landed / min 4.64 6.18
  2. Striking def.Striking defense 38% 59%
  3. DurabilitySig. strikes absorbed / min 7.62 5.18
  4. Takedown def.Takedown defense 75% 58%
  5. FinishingFinish rate 63% 60%
19-3-0
Record
14-6-0
—
Recent formRecent formWin–loss record over the fighter’s last five bouts, newest first, as carried in their UFC/FightMetric career stats.
—
China
Nationality
Brazil
38
Age
28
5′5″165 cm
Height — Xiong Jingnan leads
5′2″157 cm
63″160 cm
Reach
63″161 cm
—
StanceStanceWhich side a fighter leads from — a striking term, not a religious one. Orthodox: right-handed, left foot and hand forward (the common default). Southpaw: the mirror image, right side forward (usually a left-hander). Switch: changes between the two during a fight.
—
63%
Finish rateFinish % — Xiong Jingnan leadsFinish rateThe share of a fighter’s wins that ended inside the distance — by KO/TKO or submission — rather than going to the judges’ scorecards. Higher means more finishes.
60%
11
Wins by KO/TKOKO wins — Xiong Jingnan leads
6
1
Wins by submissionSub wins — Polastri leads
3
4.64
Sig. strikes landed / minStr / min — Polastri leadsSignificant strikes landed per minuteAverage number of significant strikes a fighter lands for every minute of fight time — a read on striking output and pace. From UFC/FightMetric career stats.
6.18
7.62
Sig. strikes absorbed / minAbs / min — Polastri leadsSignificant strikes absorbed per minuteAverage number of significant strikes a fighter takes for every minute of fight time. Lower is better — it means they get hit less often. From UFC/FightMetric career stats.
5.18
38%
Striking defenseStrike def. — Polastri leadsStriking defenseThe percentage of opponents’ significant strikes that do not land — strikes slipped, blocked or evaded. Higher is better. Not the same as striking accuracy, which counts your own strikes that land. From UFC/FightMetric.
59%
75%
Takedown defenseTD def. — Xiong Jingnan leadsTakedown defenseThe percentage of opponents’ takedown attempts that are stuffed. Higher means harder to put on the mat. From UFC/FightMetric.
58%
09:03
Avg. fight timeAvg. timeAverage fight timeThe mean length of the fighter’s bouts (minutes:seconds) — a rough read on whether they tend to finish early or go the distance. From UFC/FightMetric.
12:31
The Block Bali
Team
CWB Fighter

Career stats per UFC.com; recent form is each fighter's last five bouts. Record is as of fight night; career stats, recent form and win totals are the latest on file and may include this fight. Bars compare each stat on a fixed scale; the “Edge” marker flags the leading corner where the gap is meaningful. The snapshot plots five career rates — output, striking defense, durability (strikes absorbed, inverted), takedown defense and finish rate — each normalised on its own scale.

Comments

Comments are currently closed while we finish moderation and privacy controls.

Who Called It?

How the analysts' picks held up once the cage door closed.

AJ Devito
Hear it — 7:55 AJ Devito on YouTube ↗

Current pick evidence

Picked: Xiong Jingnan

Fight result: Julia Polastri · KO/TKO

Reverses his earlier lean after the weigh-ins and face-offs, citing Xiong Jingnan’s size, boxing and home-country setting.

“I'm gonna pick flip, man. I think Xiong Jingnan should be able to win.”

Track record: winner called in 175 of 264 resolved picks. How winner calls are counted

Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology

Winner Accuracy 66.3% (175 hit, 89 miss, across 264 resolved calls). Method Accuracy 58.7% (61 hit, 43 miss, across 104 method-scored calls on 264 resolved calls). Round Accuracy 77.8% (7 hit, 2 miss, across 9 round-scored calls on 264 resolved calls). Underdog Accuracy 36.4% (12 hit, 21 miss, across 33 underdog calls on 264 resolved calls).

View full track record (264 calls)
The MMA Guru
Hear it — 5:01 The MMA Guru on YouTube ↗

Current pick evidence

Picked: Xiong Jingnan · Dec

Fight result: Julia Polastri · KO/TKO

Picks Xiong Jingnan's size and experience to earn a decision.

“Jong Jingyang winning this one by decision. 30-27, 29-28.”

Track record: winner called in 213 of 322 resolved picks. How winner calls are counted

Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology

Winner Accuracy 66.1% (213 hit, 109 miss, across 322 resolved calls). Method Accuracy 53.4% (62 hit, 54 miss, across 116 method-scored calls on 322 resolved calls). Round Accuracy 35.9% (14 hit, 25 miss, across 39 round-scored calls on 322 resolved calls). Underdog Accuracy 47.4% (18 hit, 20 miss, across 38 underdog calls on 322 resolved calls).

View full track record (322 calls)
HopperMMA
Hear it — 3:36 HopperMMA on YouTube ↗

Current pick evidence

Picked: Xiong Jingnan · Dec

Fight result: Julia Polastri · KO/TKO

Picks Xiong Jingnan by decision.

“I'm going to go Jingnan by decision.”

Track record: winner called in 92 of 148 resolved picks. How winner calls are counted

Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology

Winner Accuracy 62.2% (92 hit, 56 miss, across 148 resolved calls). Method Accuracy 60.8% (45 hit, 29 miss, across 74 method-scored calls on 148 resolved calls). Round Accuracy 48.8% (20 hit, 21 miss, across 41 round-scored calls on 148 resolved calls). Underdog Accuracy 26.9% (7 hit, 19 miss, across 26 underdog calls on 148 resolved calls).

View full track record (148 calls)
MMA Prediction Guru (MMAPG)
Hear it — 14:33 MMA Prediction Guru (MMAPG) on YouTube ↗

Current pick evidence

Picked: Xiong Jingnan · Dec

Fight result: Julia Polastri · KO/TKO

Picks Xiong Jingnan to win on the scorecards.

“Jing Nan Jong picks up a decision victory.”

Track record: winner called in 41 of 69 resolved picks. How winner calls are counted

Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology

Winner Accuracy 59.4% (41 hit, 28 miss, across 69 resolved calls). Method Accuracy 57.7% (15 hit, 11 miss, across 26 method-scored calls on 69 resolved calls). Round Accuracy 12.5% (1 hit, 7 miss, across 8 round-scored calls on 69 resolved calls). Underdog Accuracy 30.8% (4 hit, 9 miss, across 13 underdog calls on 69 resolved calls).

View full track record (69 calls)
Bedtime MMA
Hear it — 2:17 Bedtime MMA on YouTube ↗

Current pick evidence

Picked: Julia Polastri · Dec

Fight result: Julia Polastri · KO/TKO

Picks Julia Polastri by decision.

“I'm going to go with Julia to win by decision. 29-28.”

Track record: winner called in 132 of 185 resolved picks. How winner calls are counted

Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology

Winner Accuracy 71.4% (132 hit, 53 miss, across 185 resolved calls). Method Accuracy 61.9% (60 hit, 37 miss, across 97 method-scored calls on 185 resolved calls). Round Accuracy 40.7% (11 hit, 16 miss, across 27 round-scored calls on 185 resolved calls). Underdog Accuracy 48.7% (19 hit, 20 miss, across 39 underdog calls on 185 resolved calls).

View full track record (185 calls)
FightIQ
Read source

Current pick evidence

Picked: Julia Polastri · Dec

Fight result: Julia Polastri · KO/TKO

FightIQ's public record lists Julia Polastri as its pick over Xiong Jingnan.

Track record: winner called in 159 of 227 resolved picks. How winner calls are counted

Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology

Winner Accuracy 70.0% (159 hit, 68 miss, across 227 resolved calls). Method Accuracy 39.9% (59 hit, 89 miss, across 148 method-scored calls on 227 resolved calls). Round Accuracy: No round picks. Underdog Accuracy 55.0% (11 hit, 9 miss, across 20 underdog calls on 227 resolved calls).

View full track record (227 calls)
JakeGerberMMA
Hear it — 10:48 JakeGerberMMA on YouTube ↗

Current pick evidence

Picked: Julia Polastri · Dec

Fight result: Julia Polastri · KO/TKO

Picks Julia Polastri by decision for her technical striking edge.

“Go with Julia Polastri. She's going to outpoint her and get it done on the cards.”

Track record: winner called in 101 of 154 resolved picks. How winner calls are counted

Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology

Winner Accuracy 65.6% (101 hit, 53 miss, across 154 resolved calls). Method Accuracy 60.0% (39 hit, 26 miss, across 65 method-scored calls on 154 resolved calls). Round Accuracy 35.7% (5 hit, 9 miss, across 14 round-scored calls on 154 resolved calls). Underdog Accuracy 33.3% (4 hit, 8 miss, across 12 underdog calls on 154 resolved calls).

View full track record (154 calls)
DFS By The Numbers
Hear it — 2:53 DFS By The Numbers on YouTube ↗

Current pick evidence

Picked: Julia Polastri

Fight result: Julia Polastri · KO/TKO

Picks Julia Polastri, contingent on her showing up to perform.

“I like Polastri to win. She should win as long as she shows up.”

Track record: winner called in 112 of 173 resolved picks. How winner calls are counted

Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology

Winner Accuracy 64.7% (112 hit, 61 miss, across 173 resolved calls). Method Accuracy 61.0% (61 hit, 39 miss, across 100 method-scored calls on 173 resolved calls). Round Accuracy 38.3% (18 hit, 29 miss, across 47 round-scored calls on 173 resolved calls). Underdog Accuracy 36.4% (8 hit, 14 miss, across 22 underdog calls on 173 resolved calls).

View full track record (173 calls)
Half The Battle
Hear it — 33:32 Half The Battle on YouTube ↗

Current pick evidence

Picked: Julia Polastri

Fight result: Julia Polastri · KO/TKO

Picks Julia Polastri for her pressure, output, and possible takedowns.

“I got Julia Pelri to come out here and beat the dog out of Jeang.”

Track record: winner called in 58 of 109 resolved picks. How winner calls are counted

Analyst track record Track record countsWinner counts resolved calls. Method and Round count only after a correct winner call. Underdog counts picks for a strict underdog in frozen pre-fight odds.Methodology

Winner Accuracy 53.2% (58 hit, 51 miss, across 109 resolved calls). Method Accuracy 71.4% (10 hit, 4 miss, across 14 method-scored calls on 109 resolved calls). Round Accuracy 66.7% (2 hit, 1 miss, across 3 round-scored calls on 109 resolved calls). Underdog Accuracy 21.4% (6 hit, 22 miss, across 28 underdog calls on 109 resolved calls).

View full track record (109 calls)

Analyst picks: Bedtime MMA Hit; FightIQ Hit; AJ Devito Miss; The MMA Guru Miss; JakeGerberMMA Hit; DFS By The Numbers Hit; HopperMMA Miss; MMA Prediction Guru (MMAPG) Miss; Half The Battle Hit.

5 of 9 called the winner.

Chart: selected analyst picks, not a win probability. Pill badge: Winner hit rate (total scored picks before this event).

The experts above are a lens, not credentials we conferred — analyst, fighter or betting desk.

Results

Each agent’s latest pre-fight call vs result; forecast dates may differ. Market: sportsbook snapshot or historic market reconstruction.

Actual Polastri · KO/TKO · R1

Closest probability Claude put 66% on Polastri.

ChatGPTForecast: 63 of 108 winner picks correct · 58% hit rate
61% Jingnan
39% Polastri
PickJingnan · DecisionActualPolastri · KO/TKO · R1
WinnerMissMethodNot applicable — the winner call missedRoundNot applicable — the winner call missedHistoric market underdogMissHistoric market underdog: UnderdogThe selected fighter had a lower market-implied chance of winning. This underdog call was a miss.Historic market underdog: underdog call, miss
ClaudeForecast: 61 of 101 winner picks correct · 60% hit rate
34% Jingnan
66% Polastri
PickPolastri · DecisionActualPolastri · KO/TKO · R1
WinnerHitMethodMissRoundNot calledHistoric market favouriteHistoric market favourite: FavouriteThe selected fighter had the higher market-implied chance of winning.Historic market favourite: favourite call
GeminiForecast: 68 of 108 winner picks correct · 63% hit rate
52% Jingnan
48% Polastri
PickJingnan · DecisionActualPolastri · KO/TKO · R1
WinnerMissMethodNot applicable — the winner call missedRoundNot applicable — the winner call missedHistoric market underdogMissHistoric market underdog: UnderdogThe selected fighter had a lower market-implied chance of winning. This underdog call was a miss.Historic market underdog: underdog call, miss
AI Predictions — latest pre-fight callsFrozen final publication identity; the calls below retain each agent’s own publication.

AI Predictions

Each agent’s latest pre-fight forecast. Dates are shown per agent.

  • ChatGPT

    63 of 108 winner picks correct · 58% hit rate

    Pick Jingnan

    Most likely: Jingnan by decision, about 50 in 100

    Win chance: Jingnan 61%, Polastri 39%.

    gpt-5.6-sol · 23 Aug

    Confidence 6 of 10 · Medium

  • Claude

    61 of 101 winner picks correct · 60% hit rate

    Pick Polastri

    Most likely: Polastri by decision, about 49 in 100

    Win chance: Jingnan 34%, Polastri 66%.

    claude-opus-5 · 24 Aug

    Confidence 7 of 10 · High

  • Gemini

    68 of 108 winner picks correct · 63% hit rate

    Pick Jingnan

    Most likely: Jingnan by decision, about 41 in 100

    Win chance: Jingnan 52%, Polastri 48%.

    gemini-3.1-pro-high · 24 Aug

    Confidence 5 of 10 · Medium

2 of 3 models pick Jingnan; 1 of 3 models pick Polastri.

Questions

The result 7 questions

Who wins, and how likely?

  • ChatGPT

    Jingnan: 61% (about 61 in 100 fights). Polastri: 39%.

  • Claude

    Polastri: 66% (about 66 in 100 fights). Jingnan: 34%.

  • Gemini

    Jingnan: 52% (about 52 in 100 fights). Polastri: 48%.

What is the single most likely outcome?

  • ChatGPT

    Jingnan by decision: 50% (about 50 in 100).

  • Claude

    Polastri by decision: 49% (about 49 in 100).

  • Gemini

    Jingnan by decision: 41% (about 41 in 100).

What are the three most likely outcomes, and why?

  • ChatGPT

    1. Jingnan by decision (50%); 2. Polastri by decision (30%); 3. Jingnan by KO/TKO (9%)

  • Claude

    1. Polastri by decision (49%); 2. Jingnan by decision (17%); 3. Jingnan by KO/TKO (15%)

  • Gemini

    1. Jingnan by decision (41%); 2. Polastri by decision (33%); 3. Jingnan by KO/TKO (10%)

How confident is the model?

  • ChatGPT

    6 of 10, based on Jingnan's 61% win chance.

  • Claude

    7 of 10, based on Polastri's 66% win chance.

  • Gemini

    5 of 10, based on Jingnan's 52% win chance.

Does it end early or go to the judges?

  • ChatGPT

    Finish (KO/TKO or submission): 20%. Decision: 80%.

  • Claude

    Finish (KO/TKO or submission): 34%. Decision: 66%.

  • Gemini

    Finish (KO/TKO or submission): 26%. Decision: 74%.

How does Jingnan win?

  • ChatGPT

    Jingnan wins 61%: KO/TKO 9%, submission 2%, decision 50%.

  • Claude

    Jingnan wins 34%: KO/TKO 15%, submission 2%, decision 17%.

  • Gemini

    Jingnan wins 52%: KO/TKO 10%, submission 1%, decision 41%.

How does Polastri win?

  • ChatGPT

    Polastri wins 39%: KO/TKO 6%, submission 3%, decision 30%.

  • Claude

    Polastri wins 66%: KO/TKO 13%, submission 4%, decision 49%.

  • Gemini

    Polastri wins 48%: KO/TKO 10%, submission 5%, decision 33%.

What if 1 question

What is the upset path?

  • ChatGPT

    Polastri's most likely upset: Polastri by decision (30%).

  • Claude

    Jingnan's most likely upset: Jingnan by decision (17%).

  • Gemini

    Polastri's most likely upset: Polastri by decision (33%).

Compared with others 1 question

Do the models agree?

  • All models

    The models split 2–1 (ChatGPT: Jingnan, Claude: Polastri, Gemini: Jingnan).

After the fight 1 question

What happened vs what the model said?

  • ChatGPT

    Result: Polastri by KO/TKO in round 1. Polastri by KO/TKO was the model's number 4 outcome. Its most likely outcome was Jingnan by decision (50%).

  • Claude

    Result: Polastri by KO/TKO in round 1. Polastri by KO/TKO was the model's number 4 outcome. Its most likely outcome was Polastri by decision (49%).

  • Gemini

    Result: Polastri by KO/TKO in round 1. Polastri by KO/TKO was the model's joint number 3 outcome. Its most likely outcome was Jingnan by decision (41%).

More questions (19)

The result 7 questions

KO/TKO vs submission vs decision overall

  • ChatGPT

    KO/TKO 15%, submission 5%, decision 80%.

  • Claude

    KO/TKO 28%, submission 6%, decision 66%.

  • Gemini

    KO/TKO 20%, submission 6%, decision 74%.

Who is more likely to finish the other?

  • ChatGPT

    Jingnan: 11%, against 9% for Polastri.

  • Claude

    Even: each finishes the other 17% of the time.

  • Gemini

    Polastri: 15%, against 11% for Jingnan.

Can Jingnan get the finish? Can Polastri?

  • ChatGPT

    Jingnan: 11% (KO/TKO 9%, submission 2%). Polastri: 9% (KO/TKO 6%, submission 3%).

  • Claude

    Jingnan: 17% (KO/TKO 15%, submission 2%). Polastri: 17% (KO/TKO 13%, submission 4%).

  • Gemini

    Jingnan: 11% (KO/TKO 10%, submission 1%). Polastri: 15% (KO/TKO 10%, submission 5%).

Who is more likely to be knocked out, and who to be submitted?

  • ChatGPT

    Jingnan is knocked out in 6% and submitted in 3%. Polastri is knocked out in 9% and submitted in 2%.

  • Claude

    Jingnan is knocked out in 13% and submitted in 4%. Polastri is knocked out in 15% and submitted in 2%.

  • Gemini

    Jingnan is knocked out in 10% and submitted in 5%. Polastri is knocked out in 10% and submitted in 1%.

How lopsided is this fight?

  • ChatGPT

    A clear favourite: 61% vs 39%.

  • Claude

    Lopsided: 66% vs 34%.

  • Gemini

    Close to a coin flip: 52% vs 48%.

Each fighter's single most likely way to win

  • ChatGPT

    Jingnan by decision: 50%. Polastri by decision: 30%.

  • Claude

    Jingnan by decision: 17%. Polastri by decision: 49%.

  • Gemini

    Jingnan by decision: 41%. Polastri by decision: 33%.

How big an upset would it be if the underdog wins?

  • ChatGPT

    Polastri wins 39% (about 1 in 3 fights): a modest upset.

  • Claude

    Jingnan wins 34% (about 1 in 3 fights): a big upset.

  • Gemini

    Polastri wins 48% (about 1 in 2 fights): close to a coin flip, not an upset.

Timing 1 question

Chance it goes to a decision

  • ChatGPT

    80%.

  • Claude

    66%.

  • Gemini

    74%.

What if 1 question

If it goes to the judges, who wins?

  • ChatGPT

    If it goes to the judges: Jingnan 63%, Polastri 38%.

  • Claude

    If it goes to the judges: Jingnan 26%, Polastri 74%.

  • Gemini

    If it goes to the judges: Jingnan 55%, Polastri 45%.

Compared with others 5 questions

Where does this model differ from the others?

  • ChatGPT

    Biggest difference: Jingnan by decision, 50% here against 29% on average for the others.

  • Claude

    Biggest difference: Jingnan by decision, 17% here against 46% on average for the others.

  • Gemini

    Biggest difference: Jingnan by decision, 41% here against 34% on average for the others.

How does it compare with analyst picks?

  • ChatGPT

    Of 9 analyst picks, 4 back Jingnan and 5 back Polastri. This model picks Jingnan (61%).

  • Claude

    Of 9 analyst picks, 4 back Jingnan and 5 back Polastri. This model picks Polastri (66%).

  • Gemini

    Of 9 analyst picks, 4 back Jingnan and 5 back Polastri. This model picks Jingnan (52%).

Which model is most confident on Jingnan, and which on Polastri?

  • All models

    On Jingnan: ChatGPT (61%). On Polastri: Claude (66%).

Where do the models disagree most?

  • All models

    Jingnan by decision: from 17% (Claude) to 50% (ChatGPT).

Which analyst agrees most with this model?

  • ChatGPT

    The MMA Guru (Jingnan by decision), MMA Prediction Guru (MMAPG) (Jingnan by decision) and HopperMMA (Jingnan by decision): the same winner and method as this model, tied; this model favours Jingnan, most likely by decision.

  • Claude

    Bedtime MMA (Polastri by decision), JakeGerberMMA (Polastri by decision) and FightIQ (Polastri by decision): the same winner and method as this model, tied; this model favours Polastri, most likely by decision.

  • Gemini

    The MMA Guru (Jingnan by decision), MMA Prediction Guru (MMAPG) (Jingnan by decision) and HopperMMA (Jingnan by decision): the same winner and method as this model, tied; this model favours Jingnan, most likely by decision.

How sure 4 questions

When was this forecast made, and by which model version?

  • ChatGPT

    On 23 Aug 2026, by gpt-5.6-sol.

  • Claude

    On 24 Aug 2026, by claude-opus-5.

  • Gemini

    On 24 Aug 2026, by gemini-3.1-pro-high.

What can't the model know?

  • FightCard

    Models research public information before the fight, such as records, styles, recent results and coverage. They cannot see inside training camps, injuries nobody has reported, or what happens on the night. A small chance is not no chance: outcomes the model rates at a few percent still happen, and big favourites lose sometimes.

How is "confidence" worked out?

  • FightCard

    Confidence restates the favourite's win chance on a 10-step scale: the win chance in tens, rounded, so 55% is 6 of 10 and 95% or more is 10 of 10. 1 to 3 reads Low, 4 to 6 Medium and 7 to 10 High. A favourite usually has at least half the chance, so most picks show 5 or more. When the model has the fighters exactly even, there is no pick and no confidence level. It is not a separate judgement by the model.

What counts as a KO, a decision or a draw?

  • FightCard

    KO/TKO includes referee, doctor and corner stoppages, and disqualifications. A decision includes a fight stopped early and scored on the judges' cards. A stoppage between rounds counts as a finish in the round that just ended. A draw and a no contest share one outcome.

After the fight 1 question

Was the actual result in this model's top 3?

  • ChatGPT

    No.

  • Claude

    No.

  • Gemini

    Yes, tied for number 3.

ChatGPT

Pick

Jingnan

Confidence 6 of 10 · Medium

Most likely: Jingnan by decision, about 50 in 100

Win chance: Jingnan 61%, Polastri 39%.

Most likely outcomes

  1. Jingnan by decision50%
  2. Polastri by decision30%
  3. Jingnan by KO/TKO9%
How it ends
  1. KO/TKO: Jingnan 9%, Polastri 6%.
  2. Submission: Jingnan 2%, Polastri 3%.
  3. Decision: Jingnan 50%, Polastri 30%.

AI model's own reasoning — not checked by FightCard

How ChatGPT sees the fight

Xiong Jingnan is the model pick by decision. The locked distribution gives the red corner a 61% overall win probability and assigns 80% of the total probability to a decision, making a judges’ result the clearest forecast.

Keys to victory

  • The locked distribution gives Xiong a 61% overall win probability, compared with 39% for Polastri.
  • Decision accounts for 80% of the total probability, while all finish outcomes combine for 20%.
  • Xiong by decision is the largest single outcome at 50%, followed by Polastri by decision at 30%.

X-factor

The main uncertainty is which fighter benefits if the bout reaches the judges, although the model favors Xiong in that scenario by 20 percentage points.

Questions

The result 7 questions

Who wins, and how likely?

  • ChatGPT

    Jingnan: 61% (about 61 in 100 fights). Polastri: 39%.

Other models' answers

  • Claude

    Polastri: 66% (about 66 in 100 fights). Jingnan: 34%.

  • Gemini

    Jingnan: 52% (about 52 in 100 fights). Polastri: 48%.

What is the single most likely outcome?

  • ChatGPT

    Jingnan by decision: 50% (about 50 in 100).

Other models' answers

  • Claude

    Polastri by decision: 49% (about 49 in 100).

  • Gemini

    Jingnan by decision: 41% (about 41 in 100).

What are the three most likely outcomes, and why?

  • ChatGPT

    1. Jingnan by decision (50%); 2. Polastri by decision (30%); 3. Jingnan by KO/TKO (9%)

Other models' answers

  • Claude

    1. Polastri by decision (49%); 2. Jingnan by decision (17%); 3. Jingnan by KO/TKO (15%)

  • Gemini

    1. Jingnan by decision (41%); 2. Polastri by decision (33%); 3. Jingnan by KO/TKO (10%)

How confident is the model?

  • ChatGPT

    6 of 10, based on Jingnan's 61% win chance.

Other models' answers

  • Claude

    7 of 10, based on Polastri's 66% win chance.

  • Gemini

    5 of 10, based on Jingnan's 52% win chance.

Does it end early or go to the judges?

  • ChatGPT

    Finish (KO/TKO or submission): 20%. Decision: 80%.

Other models' answers

  • Claude

    Finish (KO/TKO or submission): 34%. Decision: 66%.

  • Gemini

    Finish (KO/TKO or submission): 26%. Decision: 74%.

How does Jingnan win?

  • ChatGPT

    Jingnan wins 61%: KO/TKO 9%, submission 2%, decision 50%.

Other models' answers

  • Claude

    Jingnan wins 34%: KO/TKO 15%, submission 2%, decision 17%.

  • Gemini

    Jingnan wins 52%: KO/TKO 10%, submission 1%, decision 41%.

How does Polastri win?

  • ChatGPT

    Polastri wins 39%: KO/TKO 6%, submission 3%, decision 30%.

Other models' answers

  • Claude

    Polastri wins 66%: KO/TKO 13%, submission 4%, decision 49%.

  • Gemini

    Polastri wins 48%: KO/TKO 10%, submission 5%, decision 33%.

What if 1 question

What is the upset path?

  • ChatGPT

    Polastri's most likely upset: Polastri by decision (30%).

Other models' answers

  • Claude

    Jingnan's most likely upset: Jingnan by decision (17%).

  • Gemini

    Polastri's most likely upset: Polastri by decision (33%).

Compared with others 1 question

Do the models agree?

  • ChatGPT

    The models split 2–1 (ChatGPT: Jingnan, Claude: Polastri, Gemini: Jingnan).

After the fight 1 question

What happened vs what the model said?

  • ChatGPT

    Result: Polastri by KO/TKO in round 1. Polastri by KO/TKO was the model's number 4 outcome. Its most likely outcome was Jingnan by decision (50%).

Other models' answers

  • Claude

    Result: Polastri by KO/TKO in round 1. Polastri by KO/TKO was the model's number 4 outcome. Its most likely outcome was Polastri by decision (49%).

  • Gemini

    Result: Polastri by KO/TKO in round 1. Polastri by KO/TKO was the model's joint number 3 outcome. Its most likely outcome was Jingnan by decision (41%).

More questions (19)

The result 7 questions

KO/TKO vs submission vs decision overall

  • ChatGPT

    KO/TKO 15%, submission 5%, decision 80%.

Other models' answers

  • Claude

    KO/TKO 28%, submission 6%, decision 66%.

  • Gemini

    KO/TKO 20%, submission 6%, decision 74%.

Who is more likely to finish the other?

  • ChatGPT

    Jingnan: 11%, against 9% for Polastri.

Other models' answers

  • Claude

    Even: each finishes the other 17% of the time.

  • Gemini

    Polastri: 15%, against 11% for Jingnan.

Can Jingnan get the finish? Can Polastri?

  • ChatGPT

    Jingnan: 11% (KO/TKO 9%, submission 2%). Polastri: 9% (KO/TKO 6%, submission 3%).

Other models' answers

  • Claude

    Jingnan: 17% (KO/TKO 15%, submission 2%). Polastri: 17% (KO/TKO 13%, submission 4%).

  • Gemini

    Jingnan: 11% (KO/TKO 10%, submission 1%). Polastri: 15% (KO/TKO 10%, submission 5%).

Who is more likely to be knocked out, and who to be submitted?

  • ChatGPT

    Jingnan is knocked out in 6% and submitted in 3%. Polastri is knocked out in 9% and submitted in 2%.

Other models' answers

  • Claude

    Jingnan is knocked out in 13% and submitted in 4%. Polastri is knocked out in 15% and submitted in 2%.

  • Gemini

    Jingnan is knocked out in 10% and submitted in 5%. Polastri is knocked out in 10% and submitted in 1%.

How lopsided is this fight?

  • ChatGPT

    A clear favourite: 61% vs 39%.

Other models' answers

  • Claude

    Lopsided: 66% vs 34%.

  • Gemini

    Close to a coin flip: 52% vs 48%.

Each fighter's single most likely way to win

  • ChatGPT

    Jingnan by decision: 50%. Polastri by decision: 30%.

Other models' answers

  • Claude

    Jingnan by decision: 17%. Polastri by decision: 49%.

  • Gemini

    Jingnan by decision: 41%. Polastri by decision: 33%.

How big an upset would it be if the underdog wins?

  • ChatGPT

    Polastri wins 39% (about 1 in 3 fights): a modest upset.

Other models' answers

  • Claude

    Jingnan wins 34% (about 1 in 3 fights): a big upset.

  • Gemini

    Polastri wins 48% (about 1 in 2 fights): close to a coin flip, not an upset.

Timing 1 question

Chance it goes to a decision

  • ChatGPT

    80%.

Other models' answers

  • Claude

    66%.

  • Gemini

    74%.

What if 1 question

If it goes to the judges, who wins?

  • ChatGPT

    If it goes to the judges: Jingnan 63%, Polastri 38%.

Other models' answers

  • Claude

    If it goes to the judges: Jingnan 26%, Polastri 74%.

  • Gemini

    If it goes to the judges: Jingnan 55%, Polastri 45%.

Compared with others 5 questions

Where does this model differ from the others?

  • ChatGPT

    Biggest difference: Jingnan by decision, 50% here against 29% on average for the others.

Other models' answers

  • Claude

    Biggest difference: Jingnan by decision, 17% here against 46% on average for the others.

  • Gemini

    Biggest difference: Jingnan by decision, 41% here against 34% on average for the others.

How does it compare with analyst picks?

  • ChatGPT

    Of 9 analyst picks, 4 back Jingnan and 5 back Polastri. This model picks Jingnan (61%).

Other models' answers

  • Claude

    Of 9 analyst picks, 4 back Jingnan and 5 back Polastri. This model picks Polastri (66%).

  • Gemini

    Of 9 analyst picks, 4 back Jingnan and 5 back Polastri. This model picks Jingnan (52%).

Which model is most confident on Jingnan, and which on Polastri?

  • ChatGPT

    On Jingnan: ChatGPT (61%). On Polastri: Claude (66%).

Where do the models disagree most?

  • ChatGPT

    Jingnan by decision: from 17% (Claude) to 50% (ChatGPT).

Which analyst agrees most with this model?

  • ChatGPT

    The MMA Guru (Jingnan by decision), MMA Prediction Guru (MMAPG) (Jingnan by decision) and HopperMMA (Jingnan by decision): the same winner and method as this model, tied; this model favours Jingnan, most likely by decision.

Other models' answers

  • Claude

    Bedtime MMA (Polastri by decision), JakeGerberMMA (Polastri by decision) and FightIQ (Polastri by decision): the same winner and method as this model, tied; this model favours Polastri, most likely by decision.

How sure 4 questions

When was this forecast made, and by which model version?

  • ChatGPT

    On 23 Aug 2026, by gpt-5.6-sol.

Other models' answers

  • Claude

    On 24 Aug 2026, by claude-opus-5.

  • Gemini

    On 24 Aug 2026, by gemini-3.1-pro-high.

What can't the model know?

  • FightCard

    Models research public information before the fight, such as records, styles, recent results and coverage. They cannot see inside training camps, injuries nobody has reported, or what happens on the night. A small chance is not no chance: outcomes the model rates at a few percent still happen, and big favourites lose sometimes.

How is "confidence" worked out?

  • FightCard

    Confidence restates the favourite's win chance on a 10-step scale: the win chance in tens, rounded, so 55% is 6 of 10 and 95% or more is 10 of 10. 1 to 3 reads Low, 4 to 6 Medium and 7 to 10 High. A favourite usually has at least half the chance, so most picks show 5 or more. When the model has the fighters exactly even, there is no pick and no confidence level. It is not a separate judgement by the model.

What counts as a KO, a decision or a draw?

  • FightCard

    KO/TKO includes referee, doctor and corner stoppages, and disqualifications. A decision includes a fight stopped early and scored on the judges' cards. A stoppage between rounds counts as a finish in the round that just ended. A draw and a no contest share one outcome.

After the fight 1 question

Was the actual result in this model's top 3?

  • ChatGPT

    No.

Other models' answers

  • Gemini

    Yes, tied for number 3.

gpt-5.6-sol · 23 Aug63 of 108 winner picks correct · 58% hit rate

Claude

Pick

Polastri

Confidence 7 of 10 · High

Most likely: Polastri by decision, about 49 in 100

Win chance: Jingnan 34%, Polastri 66%.

Most likely outcomes

  1. Polastri by decision49%
  2. Jingnan by decision17%
  3. Jingnan by KO/TKO15%
How it ends
  1. KO/TKO: Jingnan 15%, Polastri 13%.
  2. Submission: Jingnan 2%, Polastri 4%.
  3. Decision: Jingnan 17%, Polastri 49%.

AI model's own reasoning — not checked by FightCard

How Claude sees the fight

Julia Polastri is the right side, but near fair value rather than a bargain. Xiong Jingnan's May 2026 loss to Angela Hill (30-27 x3, outlanded every round) is the template: volume and clinch pressure over three rounds is what a 38-year-old with three fights since Oct 2022 and a new 115 lb cut handles worst. Polastri wins striking-led fights and loses to out-workers and grapplers; Xiong is neither. The dog case is Xiong's real KO power (11 of 19 wins), the Shanghai crowd, and the chance the debut was a one-off. Most likely: Julia Polastri by decision.

Keys to victory

  • Hill template: Xiong Jingnan was shut out 30-27 x3 by volume and clinch pressure in May; Julia Polastri is a Muay Thai pressure striker at 57% accuracy
  • Age and activity: Xiong Jingnan is 38 with three fights since Oct 2022 and a second 115 lb cut on a 13-week turnaround; Julia Polastri is 28 and active
  • Grappling is a non-path for both: Julia Polastri has 5 UFC takedown attempts and 58% TDD, and Xiong Jingnan is not takedown-heavy, so pace decides

X-factor

Xiong Jingnan's boxing power is the equalizer: Julia Polastri has never been finished in the UFC but takes volume in exchanges, and one clean counter in Shanghai flips this instantly.

Questions

The result 7 questions

Who wins, and how likely?

  • Claude

    Polastri: 66% (about 66 in 100 fights). Jingnan: 34%.

Other models' answers

  • ChatGPT

    Jingnan: 61% (about 61 in 100 fights). Polastri: 39%.

  • Gemini

    Jingnan: 52% (about 52 in 100 fights). Polastri: 48%.

What is the single most likely outcome?

  • Claude

    Polastri by decision: 49% (about 49 in 100).

Other models' answers

  • ChatGPT

    Jingnan by decision: 50% (about 50 in 100).

  • Gemini

    Jingnan by decision: 41% (about 41 in 100).

What are the three most likely outcomes, and why?

  • Claude

    1. Polastri by decision (49%); 2. Jingnan by decision (17%); 3. Jingnan by KO/TKO (15%)

Other models' answers

  • ChatGPT

    1. Jingnan by decision (50%); 2. Polastri by decision (30%); 3. Jingnan by KO/TKO (9%)

  • Gemini

    1. Jingnan by decision (41%); 2. Polastri by decision (33%); 3. Jingnan by KO/TKO (10%)

How confident is the model?

  • Claude

    7 of 10, based on Polastri's 66% win chance.

Other models' answers

  • ChatGPT

    6 of 10, based on Jingnan's 61% win chance.

  • Gemini

    5 of 10, based on Jingnan's 52% win chance.

Does it end early or go to the judges?

  • Claude

    Finish (KO/TKO or submission): 34%. Decision: 66%.

Other models' answers

  • ChatGPT

    Finish (KO/TKO or submission): 20%. Decision: 80%.

  • Gemini

    Finish (KO/TKO or submission): 26%. Decision: 74%.

How does Jingnan win?

  • Claude

    Jingnan wins 34%: KO/TKO 15%, submission 2%, decision 17%.

Other models' answers

  • ChatGPT

    Jingnan wins 61%: KO/TKO 9%, submission 2%, decision 50%.

  • Gemini

    Jingnan wins 52%: KO/TKO 10%, submission 1%, decision 41%.

How does Polastri win?

  • Claude

    Polastri wins 66%: KO/TKO 13%, submission 4%, decision 49%.

Other models' answers

  • ChatGPT

    Polastri wins 39%: KO/TKO 6%, submission 3%, decision 30%.

  • Gemini

    Polastri wins 48%: KO/TKO 10%, submission 5%, decision 33%.

What if 1 question

What is the upset path?

  • Claude

    Jingnan's most likely upset: Jingnan by decision (17%).

Other models' answers

  • ChatGPT

    Polastri's most likely upset: Polastri by decision (30%).

  • Gemini

    Polastri's most likely upset: Polastri by decision (33%).

Compared with others 1 question

Do the models agree?

  • Claude

    The models split 2–1 (ChatGPT: Jingnan, Claude: Polastri, Gemini: Jingnan).

After the fight 1 question

What happened vs what the model said?

  • Claude

    Result: Polastri by KO/TKO in round 1. Polastri by KO/TKO was the model's number 4 outcome. Its most likely outcome was Polastri by decision (49%).

Other models' answers

  • ChatGPT

    Result: Polastri by KO/TKO in round 1. Polastri by KO/TKO was the model's number 4 outcome. Its most likely outcome was Jingnan by decision (50%).

  • Gemini

    Result: Polastri by KO/TKO in round 1. Polastri by KO/TKO was the model's joint number 3 outcome. Its most likely outcome was Jingnan by decision (41%).

More questions (19)

The result 7 questions

KO/TKO vs submission vs decision overall

  • Claude

    KO/TKO 28%, submission 6%, decision 66%.

Other models' answers

  • ChatGPT

    KO/TKO 15%, submission 5%, decision 80%.

  • Gemini

    KO/TKO 20%, submission 6%, decision 74%.

Who is more likely to finish the other?

  • Claude

    Even: each finishes the other 17% of the time.

Other models' answers

  • ChatGPT

    Jingnan: 11%, against 9% for Polastri.

  • Gemini

    Polastri: 15%, against 11% for Jingnan.

Can Jingnan get the finish? Can Polastri?

  • Claude

    Jingnan: 17% (KO/TKO 15%, submission 2%). Polastri: 17% (KO/TKO 13%, submission 4%).

Other models' answers

  • ChatGPT

    Jingnan: 11% (KO/TKO 9%, submission 2%). Polastri: 9% (KO/TKO 6%, submission 3%).

  • Gemini

    Jingnan: 11% (KO/TKO 10%, submission 1%). Polastri: 15% (KO/TKO 10%, submission 5%).

Who is more likely to be knocked out, and who to be submitted?

  • Claude

    Jingnan is knocked out in 13% and submitted in 4%. Polastri is knocked out in 15% and submitted in 2%.

Other models' answers

  • ChatGPT

    Jingnan is knocked out in 6% and submitted in 3%. Polastri is knocked out in 9% and submitted in 2%.

  • Gemini

    Jingnan is knocked out in 10% and submitted in 5%. Polastri is knocked out in 10% and submitted in 1%.

How lopsided is this fight?

  • Claude

    Lopsided: 66% vs 34%.

Other models' answers

  • ChatGPT

    A clear favourite: 61% vs 39%.

  • Gemini

    Close to a coin flip: 52% vs 48%.

Each fighter's single most likely way to win

  • Claude

    Jingnan by decision: 17%. Polastri by decision: 49%.

Other models' answers

  • ChatGPT

    Jingnan by decision: 50%. Polastri by decision: 30%.

  • Gemini

    Jingnan by decision: 41%. Polastri by decision: 33%.

How big an upset would it be if the underdog wins?

  • Claude

    Jingnan wins 34% (about 1 in 3 fights): a big upset.

Other models' answers

  • ChatGPT

    Polastri wins 39% (about 1 in 3 fights): a modest upset.

  • Gemini

    Polastri wins 48% (about 1 in 2 fights): close to a coin flip, not an upset.

Timing 1 question

Chance it goes to a decision

  • Claude

    66%.

Other models' answers

  • ChatGPT

    80%.

  • Gemini

    74%.

What if 1 question

If it goes to the judges, who wins?

  • Claude

    If it goes to the judges: Jingnan 26%, Polastri 74%.

Other models' answers

  • ChatGPT

    If it goes to the judges: Jingnan 63%, Polastri 38%.

  • Gemini

    If it goes to the judges: Jingnan 55%, Polastri 45%.

Compared with others 5 questions

Where does this model differ from the others?

  • Claude

    Biggest difference: Jingnan by decision, 17% here against 46% on average for the others.

Other models' answers

  • ChatGPT

    Biggest difference: Jingnan by decision, 50% here against 29% on average for the others.

  • Gemini

    Biggest difference: Jingnan by decision, 41% here against 34% on average for the others.

How does it compare with analyst picks?

  • Claude

    Of 9 analyst picks, 4 back Jingnan and 5 back Polastri. This model picks Polastri (66%).

Other models' answers

  • ChatGPT

    Of 9 analyst picks, 4 back Jingnan and 5 back Polastri. This model picks Jingnan (61%).

  • Gemini

    Of 9 analyst picks, 4 back Jingnan and 5 back Polastri. This model picks Jingnan (52%).

Which model is most confident on Jingnan, and which on Polastri?

  • Claude

    On Jingnan: ChatGPT (61%). On Polastri: Claude (66%).

Where do the models disagree most?

  • Claude

    Jingnan by decision: from 17% (Claude) to 50% (ChatGPT).

Which analyst agrees most with this model?

  • Claude

    Bedtime MMA (Polastri by decision), JakeGerberMMA (Polastri by decision) and FightIQ (Polastri by decision): the same winner and method as this model, tied; this model favours Polastri, most likely by decision.

Other models' answers

  • ChatGPT

    The MMA Guru (Jingnan by decision), MMA Prediction Guru (MMAPG) (Jingnan by decision) and HopperMMA (Jingnan by decision): the same winner and method as this model, tied; this model favours Jingnan, most likely by decision.

  • Gemini

    The MMA Guru (Jingnan by decision), MMA Prediction Guru (MMAPG) (Jingnan by decision) and HopperMMA (Jingnan by decision): the same winner and method as this model, tied; this model favours Jingnan, most likely by decision.

How sure 4 questions

When was this forecast made, and by which model version?

  • Claude

    On 24 Aug 2026, by claude-opus-5.

Other models' answers

  • ChatGPT

    On 23 Aug 2026, by gpt-5.6-sol.

  • Gemini

    On 24 Aug 2026, by gemini-3.1-pro-high.

What can't the model know?

  • FightCard

    Models research public information before the fight, such as records, styles, recent results and coverage. They cannot see inside training camps, injuries nobody has reported, or what happens on the night. A small chance is not no chance: outcomes the model rates at a few percent still happen, and big favourites lose sometimes.

How is "confidence" worked out?

  • FightCard

    Confidence restates the favourite's win chance on a 10-step scale: the win chance in tens, rounded, so 55% is 6 of 10 and 95% or more is 10 of 10. 1 to 3 reads Low, 4 to 6 Medium and 7 to 10 High. A favourite usually has at least half the chance, so most picks show 5 or more. When the model has the fighters exactly even, there is no pick and no confidence level. It is not a separate judgement by the model.

What counts as a KO, a decision or a draw?

  • FightCard

    KO/TKO includes referee, doctor and corner stoppages, and disqualifications. A decision includes a fight stopped early and scored on the judges' cards. A stoppage between rounds counts as a finish in the round that just ended. A draw and a no contest share one outcome.

After the fight 1 question

Was the actual result in this model's top 3?

  • Claude

    No.

Other models' answers

  • Gemini

    Yes, tied for number 3.

claude-opus-5 · 24 Aug61 of 101 winner picks correct · 60% hit rate

Gemini

Pick

Jingnan

Confidence 5 of 10 · Medium

Most likely: Jingnan by decision, about 41 in 100

Win chance: Jingnan 52%, Polastri 48%.

Most likely outcomes

  1. Jingnan by decision41%
  2. Polastri by decision33%
  3. Jingnan by KO/TKO, tied for number 310%
How it ends
  1. KO/TKO: Jingnan 10%, Polastri 10%.
  2. Submission: Jingnan 1%, Polastri 5%.
  3. Decision: Jingnan 41%, Polastri 33%.

AI model's own reasoning — not checked by FightCard

How Gemini sees the fight

Xiong "The Panda" Jingnan faces Julia "Psycho" Polastri in a critical strawweight bout in Shanghai. Jingnan brings elite championship experience from ONE Championship and a heavy-handed boxing style, looking to rebound from her UFC debut loss. Polastri relies on aggressive Muay Thai and kicks. At 38 years old and adapting to the 115-pound limit, Jingnan's stamina could be tested, but her home-country advantage and technical striking give her a slight edge to outpoint Polastri in a competitive striking battle over three rounds.

Keys to victory

  • Xiong Jingnan's adaptation to the strict UFC 115 lbs limit and how it impacts her stamina at 38 years old against Julia Polastri.
  • The home-country advantage for Xiong Jingnan fighting in Shanghai against Julia Polastri.
  • The striking style clash between Xiong Jingnan's boxing and sanshou base and Julia Polastri's Muay Thai.

X-factor

How well Xiong Jingnan's cardio holds up under the strict 115-pound weight cut and against Julia Polastri's pace.

Questions

The result 7 questions

Who wins, and how likely?

  • Gemini

    Jingnan: 52% (about 52 in 100 fights). Polastri: 48%.

Other models' answers

  • ChatGPT

    Jingnan: 61% (about 61 in 100 fights). Polastri: 39%.

  • Claude

    Polastri: 66% (about 66 in 100 fights). Jingnan: 34%.

What is the single most likely outcome?

  • Gemini

    Jingnan by decision: 41% (about 41 in 100).

Other models' answers

  • ChatGPT

    Jingnan by decision: 50% (about 50 in 100).

  • Claude

    Polastri by decision: 49% (about 49 in 100).

What are the three most likely outcomes, and why?

  • Gemini

    1. Jingnan by decision (41%); 2. Polastri by decision (33%); 3. Jingnan by KO/TKO (10%)

Other models' answers

  • ChatGPT

    1. Jingnan by decision (50%); 2. Polastri by decision (30%); 3. Jingnan by KO/TKO (9%)

  • Claude

    1. Polastri by decision (49%); 2. Jingnan by decision (17%); 3. Jingnan by KO/TKO (15%)

How confident is the model?

  • Gemini

    5 of 10, based on Jingnan's 52% win chance.

Other models' answers

  • ChatGPT

    6 of 10, based on Jingnan's 61% win chance.

  • Claude

    7 of 10, based on Polastri's 66% win chance.

Does it end early or go to the judges?

  • Gemini

    Finish (KO/TKO or submission): 26%. Decision: 74%.

Other models' answers

  • ChatGPT

    Finish (KO/TKO or submission): 20%. Decision: 80%.

  • Claude

    Finish (KO/TKO or submission): 34%. Decision: 66%.

How does Jingnan win?

  • Gemini

    Jingnan wins 52%: KO/TKO 10%, submission 1%, decision 41%.

Other models' answers

  • ChatGPT

    Jingnan wins 61%: KO/TKO 9%, submission 2%, decision 50%.

  • Claude

    Jingnan wins 34%: KO/TKO 15%, submission 2%, decision 17%.

How does Polastri win?

  • Gemini

    Polastri wins 48%: KO/TKO 10%, submission 5%, decision 33%.

Other models' answers

  • ChatGPT

    Polastri wins 39%: KO/TKO 6%, submission 3%, decision 30%.

  • Claude

    Polastri wins 66%: KO/TKO 13%, submission 4%, decision 49%.

What if 1 question

What is the upset path?

  • Gemini

    Polastri's most likely upset: Polastri by decision (33%).

Other models' answers

  • ChatGPT

    Polastri's most likely upset: Polastri by decision (30%).

  • Claude

    Jingnan's most likely upset: Jingnan by decision (17%).

Compared with others 1 question

Do the models agree?

  • Gemini

    The models split 2–1 (ChatGPT: Jingnan, Claude: Polastri, Gemini: Jingnan).

After the fight 1 question

What happened vs what the model said?

  • Gemini

    Result: Polastri by KO/TKO in round 1. Polastri by KO/TKO was the model's joint number 3 outcome. Its most likely outcome was Jingnan by decision (41%).

Other models' answers

  • ChatGPT

    Result: Polastri by KO/TKO in round 1. Polastri by KO/TKO was the model's number 4 outcome. Its most likely outcome was Jingnan by decision (50%).

  • Claude

    Result: Polastri by KO/TKO in round 1. Polastri by KO/TKO was the model's number 4 outcome. Its most likely outcome was Polastri by decision (49%).

More questions (19)

The result 7 questions

KO/TKO vs submission vs decision overall

  • Gemini

    KO/TKO 20%, submission 6%, decision 74%.

Other models' answers

  • ChatGPT

    KO/TKO 15%, submission 5%, decision 80%.

  • Claude

    KO/TKO 28%, submission 6%, decision 66%.

Who is more likely to finish the other?

  • Gemini

    Polastri: 15%, against 11% for Jingnan.

Other models' answers

  • ChatGPT

    Jingnan: 11%, against 9% for Polastri.

  • Claude

    Even: each finishes the other 17% of the time.

Can Jingnan get the finish? Can Polastri?

  • Gemini

    Jingnan: 11% (KO/TKO 10%, submission 1%). Polastri: 15% (KO/TKO 10%, submission 5%).

Other models' answers

  • ChatGPT

    Jingnan: 11% (KO/TKO 9%, submission 2%). Polastri: 9% (KO/TKO 6%, submission 3%).

  • Claude

    Jingnan: 17% (KO/TKO 15%, submission 2%). Polastri: 17% (KO/TKO 13%, submission 4%).

Who is more likely to be knocked out, and who to be submitted?

  • Gemini

    Jingnan is knocked out in 10% and submitted in 5%. Polastri is knocked out in 10% and submitted in 1%.

Other models' answers

  • ChatGPT

    Jingnan is knocked out in 6% and submitted in 3%. Polastri is knocked out in 9% and submitted in 2%.

  • Claude

    Jingnan is knocked out in 13% and submitted in 4%. Polastri is knocked out in 15% and submitted in 2%.

How lopsided is this fight?

  • Gemini

    Close to a coin flip: 52% vs 48%.

Other models' answers

  • ChatGPT

    A clear favourite: 61% vs 39%.

  • Claude

    Lopsided: 66% vs 34%.

Each fighter's single most likely way to win

  • Gemini

    Jingnan by decision: 41%. Polastri by decision: 33%.

Other models' answers

  • ChatGPT

    Jingnan by decision: 50%. Polastri by decision: 30%.

  • Claude

    Jingnan by decision: 17%. Polastri by decision: 49%.

How big an upset would it be if the underdog wins?

  • Gemini

    Polastri wins 48% (about 1 in 2 fights): close to a coin flip, not an upset.

Other models' answers

  • ChatGPT

    Polastri wins 39% (about 1 in 3 fights): a modest upset.

  • Claude

    Jingnan wins 34% (about 1 in 3 fights): a big upset.

Timing 1 question

Chance it goes to a decision

  • Gemini

    74%.

Other models' answers

  • ChatGPT

    80%.

  • Claude

    66%.

What if 1 question

If it goes to the judges, who wins?

  • Gemini

    If it goes to the judges: Jingnan 55%, Polastri 45%.

Other models' answers

  • ChatGPT

    If it goes to the judges: Jingnan 63%, Polastri 38%.

  • Claude

    If it goes to the judges: Jingnan 26%, Polastri 74%.

Compared with others 5 questions

Where does this model differ from the others?

  • Gemini

    Biggest difference: Jingnan by decision, 41% here against 34% on average for the others.

Other models' answers

  • ChatGPT

    Biggest difference: Jingnan by decision, 50% here against 29% on average for the others.

  • Claude

    Biggest difference: Jingnan by decision, 17% here against 46% on average for the others.

How does it compare with analyst picks?

  • Gemini

    Of 9 analyst picks, 4 back Jingnan and 5 back Polastri. This model picks Jingnan (52%).

Other models' answers

  • ChatGPT

    Of 9 analyst picks, 4 back Jingnan and 5 back Polastri. This model picks Jingnan (61%).

  • Claude

    Of 9 analyst picks, 4 back Jingnan and 5 back Polastri. This model picks Polastri (66%).

Which model is most confident on Jingnan, and which on Polastri?

  • Gemini

    On Jingnan: ChatGPT (61%). On Polastri: Claude (66%).

Where do the models disagree most?

  • Gemini

    Jingnan by decision: from 17% (Claude) to 50% (ChatGPT).

Which analyst agrees most with this model?

  • Gemini

    The MMA Guru (Jingnan by decision), MMA Prediction Guru (MMAPG) (Jingnan by decision) and HopperMMA (Jingnan by decision): the same winner and method as this model, tied; this model favours Jingnan, most likely by decision.

Other models' answers

  • Claude

    Bedtime MMA (Polastri by decision), JakeGerberMMA (Polastri by decision) and FightIQ (Polastri by decision): the same winner and method as this model, tied; this model favours Polastri, most likely by decision.

How sure 4 questions

When was this forecast made, and by which model version?

  • Gemini

    On 24 Aug 2026, by gemini-3.1-pro-high.

Other models' answers

  • ChatGPT

    On 23 Aug 2026, by gpt-5.6-sol.

  • Claude

    On 24 Aug 2026, by claude-opus-5.

What can't the model know?

  • FightCard

    Models research public information before the fight, such as records, styles, recent results and coverage. They cannot see inside training camps, injuries nobody has reported, or what happens on the night. A small chance is not no chance: outcomes the model rates at a few percent still happen, and big favourites lose sometimes.

How is "confidence" worked out?

  • FightCard

    Confidence restates the favourite's win chance on a 10-step scale: the win chance in tens, rounded, so 55% is 6 of 10 and 95% or more is 10 of 10. 1 to 3 reads Low, 4 to 6 Medium and 7 to 10 High. A favourite usually has at least half the chance, so most picks show 5 or more. When the model has the fighters exactly even, there is no pick and no confidence level. It is not a separate judgement by the model.

What counts as a KO, a decision or a draw?

  • FightCard

    KO/TKO includes referee, doctor and corner stoppages, and disqualifications. A decision includes a fight stopped early and scored on the judges' cards. A stoppage between rounds counts as a finish in the round that just ended. A draw and a no contest share one outcome.

After the fight 1 question

Was the actual result in this model's top 3?

  • Gemini

    Yes, tied for number 3.

Other models' answers

  • ChatGPT

    No.

  • Claude

    No.

gemini-3.1-pro-high · 24 Aug68 of 108 winner picks correct · 63% hit rate

AI-generated · Not betting advice · 21+. Gambling problem? Call 1-800-MY-RESET

Market Odds

No current consensus line is saved on this page.

Not betting advice · 21+. Gambling problem? Call 1-800-MY-RESET

Independent fan-made fight recap. Not affiliated with, endorsed by, or sponsored by the UFC or any other MMA promotion. Analysis is editorial opinion, not betting advice. Fighter names and records are used for commentary. Image credits · Methodology · Privacy · Terms.